Evals for Every Language - Acehnese (ace): leaderboard
Average score across evaluation tasks in Acehnese (ace), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 65 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 76.82 | #58 |
| 2 | Claude Opus 4.7 | 75.48 | #49 |
| 3 | Gemini 3.1 Flash Lite | 73.88 | #191 |
| 4 | GPT-5.5 | 72.1 | #31 |
| 5 | Claude Opus 4.8 | 71.95 | #37 |
| 6 | Qwen 3.6 Plus | 70.57 | #120 |
| 7 | GPT-5 | 70.19 | #98 |
| 8 | Gemini 2.5 Pro | 70.06 | #152 |
| 9 | GPT-5.3 | 70.01 | #103 |
| 10 | Grok 4.20 | 68.66 | #175 |
| 11 | Claude Sonnet 4.6 | 68.08 | #90 |
| 12 | GPT-5.4 | 68.06 | #79 |
| 13 | Claude Sonnet 4.5 | 68.01 | #142 |
| 14 | Claude Sonnet 4 | 67.89 | #199 |
| 15 | DeepSeek V3.2 Exp | 64.87 | #234 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-ace · How It Works · Data refreshed daily, snapshot 2026-10-20.